{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-video-object-segmentation-from","title":"Learning Video Object Segmentation from Static Images","arxiv_id":"1612.02646","date":"2016-12-08","proceeding":"CVPR 2017 7","authors":["Anna Khoreva","Federico Perazzi","Rodrigo Benenson","Bernt Schiele","Alexander Sorkine-Hornung"],"abstract":"Inspired by recent advances of deep learning in instance segmentation and\nobject tracking, we introduce video object segmentation problem as a concept of\nguided instance segmentation. Our model proceeds on a per-frame basis, guided\nby the output of the previous frame towards the object of interest in the next\nframe. We demonstrate that highly accurate object segmentation in videos can be\nenabled by using a convnet trained with static images only. The key ingredient\nof our approach is a combination of offline and online learning strategies,\nwhere the former serves to produce a refined mask from the previous frame\nestimate and the latter allows to capture the appearance of the specific object\ninstance. Our method can handle different types of input annotations: bounding\nboxes and segments, as well as incorporate multiple annotated frames, making\nthe system suitable for diverse applications. We obtain competitive results on\nthree different datasets, independently from the type of input annotation.","url_abs":"http://arxiv.org/abs/1612.02646v1","url_pdf":"http://arxiv.org/pdf/1612.02646v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-video-object-segmentation-from","repo_url":"https://github.com/birdman9390/MetaMaskTrack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-video-object-segmentation-from","repo_url":"https://github.com/omkar13/MaskTrack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-video-object-segmentation","task_name":"Semi-Supervised Video Object Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"MSK","rank_in_archive_order":65,"of":78,"metrics":{"F-measure (Decay)":"9.0","F-measure (Mean)":"75.4","F-measure (Recall)":"87.1","J&F":"77.55","Jaccard (Decay)":"8.9","Jaccard (Mean)":"79.7","Jaccard (Recall)":"93.1"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube","model":"MaskTrack","rank_in_archive_order":5,"of":5,"metrics":{"mIoU":"0.726"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.02646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.02646"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/birdman9390/MetaMaskTrack","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/omkar13/MaskTrack","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran_honours":2,"unverified":5},"by_repo_kind":{"listed":{"samples":8,"ran":3,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"birdman9390/MetaMaskTrack","repo_kind":"listed","path":"training/deeplab_resnet.py","file_url":"https://github.com/birdman9390/MetaMaskTrack/blob/HEAD/training/deeplab_resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"b3b7c1c716f4ca66","entry":"lr_poly","repo":"omkar13/MaskTrack","repo_kind":"listed","path":"training/utility_functions.py","file_url":"https://github.com/omkar13/MaskTrack/blob/HEAD/training/utility_functions.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b3b7c1c716f4ca66"}},{"code_sha256_prefix":"27504cbeb5811ea6","entry":"outS","repo":"birdman9390/MetaMaskTrack","repo_kind":"listed","path":"training/deeplab_resnet.py","file_url":"https://github.com/birdman9390/MetaMaskTrack/blob/HEAD/training/deeplab_resnet.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"27504cbeb5811ea6"}},{"code_sha256_prefix":"04449ede31497a35","entry":"Res_Deeplab","repo":"birdman9390/MetaMaskTrack","repo_kind":"listed","path":"training/deeplab_resnet.py","file_url":"https://github.com/birdman9390/MetaMaskTrack/blob/HEAD/training/deeplab_resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"04449ede31497a35"}},{"code_sha256_prefix":"c5ef366468627417","entry":"calculate_precision","repo":"omkar13/MaskTrack","repo_kind":"listed","path":"training/utility_functions.py","file_url":"https://github.com/omkar13/MaskTrack/blob/HEAD/training/utility_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c5ef366468627417"}},{"code_sha256_prefix":"d6f2082b3d061708","entry":"calculate_recall","repo":"omkar13/MaskTrack","repo_kind":"listed","path":"training/utility_functions.py","file_url":"https://github.com/omkar13/MaskTrack/blob/HEAD/training/utility_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d6f2082b3d061708"}},{"code_sha256_prefix":"77f6bd28fdfa4b9a","entry":"db_read_sequences","repo":"omkar13/MaskTrack","repo_kind":"listed","path":"training/dataloaders/config.py","file_url":"https://github.com/omkar13/MaskTrack/blob/HEAD/training/dataloaders/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"77f6bd28fdfa4b9a"}},{"code_sha256_prefix":"e2097a28f2129d9b","entry":"imread_indexed","repo":"omkar13/MaskTrack","repo_kind":"listed","path":"training/dataloaders/io.py","file_url":"https://github.com/omkar13/MaskTrack/blob/HEAD/training/dataloaders/io.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e2097a28f2129d9b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}